Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite annotations indicating readOnly and idempotent hints, the description discloses an important side effect: setting mark_read:true flags events as read, altering future calls. It also details the payload structure and notes that polling is safe. This adds value beyond the annotations, though it stops short of discussing rate limits or auth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is tersely written, with each sentence contributing new information. It opens with the core action, then layers in return details, filtering, mark_read semantics, and a polling note, all without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since there is no output schema, the description compensates by outlining the returned fields (source, citation_uri, raw payload). It covers filtering, mark_read side effects, polling suitability, and even provides an external endpoint. This is fully complete given the 5-parameter, no-output-schema context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the schema already documents parameters. The description adds value by providing concrete examples (e.g., type 'sec_8k') and explaining the behavioral effect of mark_read and since filters, which enriches the parameter semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Pull fired events from your subscription feed' with a specific verb and resource, and further clarifies it returns the most recent alerts with fields like source and citation_uri. This distinguishes it from sibling tools like get_feed or subscribe, which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains filtering options and the mark_read behavior, which is a clear usage context. It also provides an alternative for scripts/dashboards via a URL, implying the tool is for interactive use. However, it does not explicitly contrast with sibling tools like get_feed, so it lacks explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.